Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control

Ramesh Arvind Naagarajan, Zühal Wagner, Stefan Streif · International Conference on Machine Learning (ICML), July 2026

A framework that unifies physics knowledge graphs, KKT optimisation evidence, and temporal causal discovery to produce human-interpretable explanations for nonlinear model predictive control across greenhouse climate, building HVAC, and chemical process engineering.

Explainable AIModel Predictive ControlCausalityICML DOI

Enhancing greenhouse management with interpretable AI: a natural-language interface for advanced and optimization-based control

Ramesh Arvind Naagarajan, Kiran Kumar Sathyanarayanan, Nadja Bauer, Stefan Streif · Smart Agricultural Technology, August 2025

A natural-language interface that lets greenhouse operators query an MPC controller in plain English and receive interpretable, evidence-grounded answers about why the system acted the way it did.

Explainable AIModel Predictive ControlGreenhouseLLM DOI

Automated analysis and textual summarization of time-varying references in advanced greenhouse climate control

Ramesh Arvind Naagarajan, Kiran Kumar Sathyanarayanan, Nadja Bauer, Stefan Streif · Frontiers in Agronomy, March 2025

An automated pipeline that decomposes time-varying greenhouse reference trajectories (temperature, humidity, CO2) into operator-readable components, so domain experts can audit setpoint design at scale.

Time SeriesReference SignalsControlled-Environment Agriculture DOI

For a complete list including talks, see my Google Scholar profile.